🔌
New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
// RUN — FITS
Can the GMKtec EVO-X3 run iGPT-L?
Yes — here's how fast and up to what context, with real measured numbers.
iGPT-L on the GMKtec EVO-X3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1693k | 61.1-74.2 t/s | ~2.4-2.9 (slow) |
| Q8 | yes | 1714k | 122.2-148.5 t/s | ~4.8-5.8 (slow) |
| Q4 | yes | 1723k | 218.2-265.2 t/s | ~8.5-10.4 (slow) |
Estimate (memory-bound). Beyond "max context" the KV cache spills to SSD swap and speed drops to the "beyond" figure.
FAQ
Can the GMKtec EVO-X3 run iGPT-L?▶
Yes. At Q4 it generates ~218.2-265.2 tok/s and fits up to 1723k context; beyond that it spills to SSD swap and slows to ~8.5-10.4 tok/s.
How much context fits?▶
At Q4, up to about 1723k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.